Results 1 to 10 of about 3,555,912 (299)

Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications

Frontiers in Neuroscience, 2020
In the last few years, spiking neural networks (SNNs) have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice ...
Martino Sorbaro, Martino Sorbaro, Qian Liu, Massimo Bortone, Sadique Sheik   +4 more
doaj   +1 more source

Neuromorphic Sentiment Analysis Using Spiking Neural Networks

Sensors, 2023
Over the past decade, the artificial neural networks domain has seen a considerable embracement of deep neural networks among many applications. However, deep neural networks are typically computationally complex and consume high power, hindering their ...
Raghavendra K. Chunduri, Darshika G. Perera   +1 more
doaj   +1 more source

Financial time series prediction using spiking neural networks. [PDF]

PLoS ONE, 2014
In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction.
David Reid, Abir Jaafar Hussain, Hissam Tawfik   +2 more
doaj   +1 more source

Advancing Neural Networks: Innovations and Impacts on Energy Consumption

Advanced Electronic Materials
The energy efficiency of Artificial Intelligence (AI) systems is a crucial and actual issue that may have an important impact on an ecological, economic and technological level.
Alina Fedorova, Nikola Jovišić, Jordi Vallverdù, Silvia Battistoni, Miloš Jovičić, Milovan Medojević, Alexander Toschev, Evgeniia Alshanskaia, Max Talanov, Victor Erokhin   +9 more
doaj   +1 more source

Research on Anti-Interference Performance of Spiking Neural Network Under Network Connection Damage

Brain Sciences
Background: With the development of artificial intelligence, memristors have become an ideal choice to optimize new neural network architectures and improve computing efficiency and energy efficiency due to their combination of storage and computing ...
Yongqiang Zhang, Haijie Pang, Jinlong Ma, Guilei Ma, Xiaoming Zhang, Menghua Man   +5 more
doaj   +1 more source

High-performance deep spiking neural networks with 0.3 spikes per neuron

Nature Communications
Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks.
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec, Giovanni Cherubini, Angeliki Pantazi, Wulfram Gerstner   +5 more
doaj   +1 more source

Improving Spiking Neural Network Performance with Auxiliary Learning

Machine Learning and Knowledge Extraction, 2023
The use of back propagation through the time learning rule enabled the supervised training of deep spiking neural networks to process temporal neuromorphic data. However, their performance is still below non-spiking neural networks. Previous work pointed
Paolo G. Cachi, Sebastián Ventura, Krzysztof J. Cios   +2 more
doaj   +1 more source

Sparse Computation in Adaptive Spiking Neural Networks

Frontiers in Neuroscience, 2019
Artificial Neural Networks (ANNs) are bio-inspired models of neural computation that have proven highly effective. Still, ANNs lack a natural notion of time, and neural units in ANNs exchange analog values in a frame-based manner, a computationally and ...
Davide Zambrano, Roeland Nusselder, H. Steven Scholte, Sander M. Bohté, Sander M. Bohté   +4 more
doaj   +1 more source

Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates.

PLoS Computational Biology
Training spiking recurrent neural networks (SRNNs) presents significant challenges compared to standard recurrent neural networks (RNNs) that model neural firing rates more directly.
Thomas Robert Newton, Wilten Nicola
doaj   +1 more source

Progress and Benchmark of Spiking Neuron Devices and Circuits

Advanced Intelligent Systems, 2021
The sustainability of ever more sophisticated artificial intelligence relies on the continual development of highly energy‐efficient and compact computing hardware that mimics the biological neural networks.
Fu-Xiang Liang, I-Ting Wang, Tuo-Hung Hou   +2 more
doaj   +1 more source